Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Emile Anand

Emile Anand

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

AI×1ML×1Systems and Control×1

Frequent co-authors

Mohammed Rehan Parwani1×
Xinyuan Cao1×

Research Timeline

2026
Adaptive Multi-Token Prediction: How far should we go?

This paper proposes Adaptive Multi-Token Prediction (AMTP), a method to accelerate language-model decoding by dynamically adjusting the speculation horizon based on verification feedback.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.LGeess.SYEmpiricalRecentOct 20, 2026

Adaptive Multi-Token Prediction: How far should we go?

Emile Anand, Mohammed Rehan Parwani, Xinyuan Cao

This paper proposes Adaptive Multi-Token Prediction (AMTP), a method to accelerate language-model decoding by dynamically adjusting the speculation horizon based on verification feedback.

View →